Linear Regression over Networks with Communication Guarantees
This work addresses communication bottlenecks in connected autonomous systems, offering incremental improvements for distributed linear regression.
The paper tackles the problem of communication-efficient distributed learning for linear regression in resource-constrained networks, such as smart cities and IoT, by developing algorithms that trade off communication and learning with theoretical guarantees and practical efficiency.
A key functionality of emerging connected autonomous systems such as smart cities, smart transportation systems, and the industrial Internet-of-Things, is the ability to process and learn from data collected at different physical locations. This is increasingly attracting attention under the terms of distributed learning and federated learning. However, in connected autonomous systems, data transfer takes place over communication networks with often limited resources. This paper examines algorithms for communication-efficient learning for linear regression tasks by exploiting the informativeness of the data. The developed algorithms enable a tradeoff between communication and learning with theoretical performance guarantees and efficient practical implementations.